Method and device for identifying common oil mixed in high oleic acid oil

Abstract

The invention relates to the technical field of seed and food authenticity identification, and provides a method and device for identifying common oil mixed in high oleic acid oil. The method comprises the following steps: acquiring near infrared spectrum data of each oil plant in hyperspectral data of a target oil plant test set; inputting the near infrared spectrum data into a discriminant analysis model to obtain discriminant values of the oil plants output by the discriminant analysis model; and if the discriminant value distribution of each oil plant accords with normal distribution, determining that the oil plant set corresponding to the hyperspectral data of the target oil plant test set is not doped with the common oil plant. According to the method and the device for identifying the common oil mixed in the high-oleic-acid oil provided by the invention, the discriminant analysis model obtained by modeling the hyperspectral feature data of the high-oleic-acid oil and the common oil is combined with normal distribution, so that the identification efficiency and the accuracy of the authenticity of the oil can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of seed and food authenticity identification, and specifically to a method and device for identifying common oil mixed in high oleic oil. Background Art

[0002] Oilseed fruits are rich in protein, fat, vitamins, minerals, a variety of essential amino acids and unsaturated fatty acids for the human body, and have the functions of promoting the development of human brain cells and enhancing memory. High oleic acid oilseeds have high oleic acid content and strong antioxidant capacity, and the shelf life of finished products or products is extended by 1 to 8 times compared with ordinary oilseeds. With the improvement of living standards, high oleic acid oilseeds have gradually become an important development direction for international oilseed production and consumption.

[0003] Traditional methods for identifying high oleic oil include gas chromatography and near-infrared spectroscopy based on photoelectromagnetic induction. The above methods detect the fatty acid content in a single grain of oil to determine whether the oleic acid content in the fatty acids reaches the high oleic oil content, thereby determining whether the single grain of oil is high oleic oil. However, on the one hand, these methods can only identify one grain of oil at a time, and it is difficult to achieve one-time rapid identification of batches of oil, resulting in low identification efficiency; on the other hand, these methods can only detect the oleic acid content in a single grain of oil, and it is difficult to eliminate the error introduced by the determination of the oleic acid content of a single grain of oil, resulting in reduced identification accuracy; on the third hand, because it is impossible to identify batches of oil at one time, it is difficult to identify whether ordinary oil is mixed in batches of high oleic oil at one time. Summary of the invention

[0004] The embodiments of the present application provide a method and device for identifying common oil mixed in high oleic oil, so as to solve the technical problems that the traditional identification method has low efficiency and accuracy, and is difficult to identify whether common oil is mixed in a batch of oil at one time.

[0005] In a first aspect, the present invention provides a method for identifying high oleic acid oil mixed with common oil, comprising: Obtain near infrared spectrum data of each oil in the target oil test set hyperspectral data; Inputting the near infrared spectrum data into a discriminant analysis model to obtain a discriminant value of each oil output by the discriminant analysis model; If the distribution of the discriminant values ​​of each oil conforms to the normal distribution, it is determined that the oil set corresponding to the hyperspectral data of the target oil test set is not mixed with ordinary oil; The discriminant analysis model is obtained by modeling the hyperspectral feature data of high oleic oil and ordinary oil using the discriminant analysis method. The high oleic oil is an oil whose oleic acid content meets the national standards, industry standards and other relevant standards, and the ordinary oil is an oil whose oleic acid content is lower than the national standards, industry standards and other relevant standards.

[0006] In one embodiment, the discriminant analysis model is modeled based on the following method: Performing black-and-white correction on hyperspectral images of multiple grains of high-oleic oil and hyperspectral images of multiple grains of common oil to obtain multiple corrected oil images; Extracting hyperspectral data of each corrected oil image; Preprocessing each hyperspectral data to obtain multiple target hyperspectral data; Extract multiple hyperspectral feature data from each target hyperspectral data in descending order of importance; The plurality of hyperspectral feature data are modeled using a partial least squares discriminant analysis method to obtain the discriminant analysis model.

[0007] In one embodiment, extracting the hyperspectral data of each corrected oil image includes: According to the spectral difference between the oil edge and the oil background at a specific wavelength in each corrected oil image, the oil body spectral image is screened out from each corrected oil image; Calculating the ratio of the sum of the spectral values ​​of each pixel in the oil-body spectral image to the number of pixels to obtain the central point spectral value of the oil-body spectral image; The center point spectral value is determined as the hyperspectral data in each corrected oil image.

[0008] In one embodiment, the preprocessing of each hyperspectral data to obtain a plurality of target hyperspectral data includes: Each hyperspectral data is preprocessed by removing background, eliminating boundary abnormal points, standard normal transformation, derivative or multivariate scattering correction, so as to obtain multiple target hyperspectral data of multiple oil grains.

[0009] In one embodiment, the target oil test set hyperspectral data is obtained based on the following method: According to the hyperspectral images of the plurality of oils to be tested, a plurality of target hyperspectral data of the plurality of oil grains in the oils to be tested are obtained; A plurality of target hyperspectral data of a plurality of oil particles in the oil to be tested are determined as the target oil test set hyperspectral data.

[0010] In one embodiment, the confidence interval of the normal distribution is 99.5%.

[0011] In a second aspect, the present application provides a device for identifying high oleic acid oil mixed with ordinary oil, comprising: The near infrared spectrum data acquisition module is used to: acquire the near infrared spectrum data of each oil in the target oil test set hyperspectral data; A discriminant analysis module, used to: input the near infrared spectrum data into a discriminant analysis model to obtain a discriminant value of each oil output by the discriminant analysis model; The identification module is used to: if the distribution of the discriminant values ​​of each oil conforms to the normal distribution, determine that the oil set corresponding to the hyperspectral data of the target oil test set is not mixed with ordinary oil; The discriminant analysis model is obtained by modeling the hyperspectral feature data of high oleic oil and ordinary oil using the discriminant analysis method. The high oleic oil is an oil whose oleic acid content meets the national standards, industry standards and other relevant standards, and the ordinary oil is an oil whose oleic acid content is lower than the national standards, industry standards and other relevant standards.

[0012] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor and a memory storing a computer program, wherein when the processor executes the program, the steps of the method for identifying high oleic oil mixed with ordinary oil described in the first aspect are implemented.

[0013] In a fourth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the method for identifying high oleic oil mixed with ordinary oil as described in the first aspect.

[0014] In a fifth aspect, an embodiment of the present application provides a non-transitory computer-readable storage medium, comprising a computer program, which, when executed by a processor, implements the steps of the method for identifying ordinary oil mixed with high oleic oil as described in the first aspect.

[0015] The present application provides a method and device for identifying common oils mixed in high oleic oils, which obtain near-infrared spectral data of each oil in the target oil test set hyperspectral data, input the near-infrared spectral data into a discriminant analysis model, and obtain a discriminant value of each oil output by the discriminant analysis model. If the distribution of the discriminant values ​​of each oil conforms to the normal distribution, it is determined that common oils are not mixed into the oil set corresponding to the hyperspectral data of the target oil test set. The discriminant analysis model is obtained by modeling the hyperspectral feature data of high oleic oils and common oils using the discriminant analysis method. High oleic oils are oils whose oleic acid content conforms to national standards, industry standards and other relevant standards, and common oils are oils whose oleic acid content is lower than national standards, industry standards and other relevant standards. Since the discriminant analysis model is constructed using the hyperspectral feature data of high-oleic oil and ordinary oil, the discriminant analysis model can be used to quickly identify batches of oil at one time, thereby improving the identification efficiency. At the same time, since the hyperspectral information of the oil can accurately characterize the oleic acid content therein, the discriminant analysis model constructed using the hyperspectral information can accurately identify the high-oleic oil and improve the identification accuracy. Furthermore, since the one-time identification of batches of oil is achieved, and the model output discriminant value of the batch of high-oleic oil usually presents a normal distribution, the normal distribution can be used to perform a one-time authenticity identification of the batch of high-oleic oil. In summary, the discriminant analysis model obtained by modeling the hyperspectral feature data of high-oleic oil and ordinary oil in this application, combined with the normal distribution, can improve the efficiency and accuracy of oil identification, and at the same time achieve a one-time authenticity identification of batches of high-oleic oil. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present application or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 This is one of the flow diagrams of the method for identifying high oleic acid oil mixed with common oil provided in the embodiments of the present application; Figure 2 This is the second flow chart of the method for identifying high oleic acid oil mixed with common oil provided in the embodiment of the present application; Figure 3 This is a distribution diagram of discrimination values ​​when the mixing ratio is 5% in the method for identifying high oleic peanuts mixed with common peanuts provided in the embodiment of the present application; Figure 4 This is a distribution diagram of discrimination values ​​when the mixing ratio is 10% in the method for identifying high oleic acid peanuts mixed with common peanuts provided in the embodiment of the present application; Figure 5This is a distribution diagram of discrimination values ​​when the mixing ratio is 15% in the method for identifying high oleic acid peanuts mixed with common peanuts provided in the embodiment of the present application; Figure 6 This is a distribution diagram of discrimination values ​​when the mixing ratio is 20% in the method for identifying high oleic acid peanuts mixed with common peanuts provided in the embodiment of the present application; Figure 7 This is a distribution diagram of discrimination values ​​when the mixing ratio is 25% in the method for identifying high oleic peanuts mixed with common peanuts provided in the embodiment of the present application; Figure 8 It is a schematic diagram of the structure of a device for identifying high oleic acid oil mixed with ordinary oil provided in an embodiment of the present application; Fig. 9 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0019] It should be noted that in the description of the embodiments of the present application, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or device including the elements. The orientation or position relationship indicated by the terms "upper", "lower" and the like is based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application. Unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, or it can be a connection between the two elements. For those skilled in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0020] The terms "first", "second", etc. in this application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0021] Figure 1 This is one of the flow diagrams of the method for identifying high oleic acid oil mixed with ordinary oil provided in the examples of this application. Figure 1 The present application provides a method for identifying high oleic acid oil mixed with common oil, which may include: 101. Obtain near infrared spectrum data of each oil in the target oil test set hyperspectral data; 102. Inputting the near infrared spectrum data into the discriminant analysis model to obtain the discriminant value of each oil output by the discriminant analysis model; 103. If the distribution of the discriminant values ​​of each oil conforms to the normal distribution, it is determined that the oil set corresponding to the hyperspectral data of the target oil test set is not mixed with ordinary oil.

[0022] The discriminant analysis model is obtained by modeling the hyperspectral feature data of high oleic acid oil and ordinary oil using the discriminant analysis method. High oleic acid oil refers to oil whose oleic acid content meets national standards, industry standards and other relevant standards. For example, the oleic acid content in high oleic acid peanuts is not less than 75%, and the oleic acid content in high oleic acid rapeseed is not less than 73%. Ordinary oil refers to oil whose oleic acid content is lower than national standards, industry standards and other relevant standards.

[0023] Furthermore, the confidence interval of the normal distribution can be set according to actual needs and is not limited here. In this embodiment, the confidence interval can be 99.5%.

[0024] In addition, in addition to using partial least squares discriminant analysis to model the hyperspectral feature data of high oleic oil and ordinary oil, support vector machine method can also be used to model the hyperspectral feature data of high oleic oil and ordinary oil, which is not limited here.

[0025] In step 103, the model output discriminant value of the batch high oleic oil usually conforms to the normal distribution, but when the ordinary oil is mixed, the normal distribution will be destroyed, resulting in a change in the normal distribution of the model output discriminant value of the batch oil mixed with the ordinary oil, which is reflected in the deviation of the model output discriminant value of the batch oil mixed with the ordinary oil from the 99.5% confidence interval of the normal distribution of the original discriminant value. Therefore, whether the target oil test set is mixed can be judged by whether the discriminant value distribution conforms to the normal distribution.

[0026] The present embodiment provides a method for identifying common oils mixed with high oleic oils, which obtains near-infrared spectral data of each oil in the target oil test set hyperspectral data, inputs the near-infrared spectral data into a discriminant analysis model, and obtains a discriminant value of each oil output by the discriminant analysis model. If the distribution of the discriminant values ​​of each oil conforms to a normal distribution, it is determined that common oils are not mixed into the oil set corresponding to the target oil test set hyperspectral data. The discriminant analysis model is obtained by modeling the hyperspectral feature data of high oleic oils and common oils using a discriminant analysis method. High oleic oils are oils whose oleic acid content conforms to relevant standards such as national standards and industry standards, and common oils are oils whose oleic acid content is lower than relevant standards such as national standards and industry standards. Since the discriminant analysis model is constructed using the hyperspectral feature data of high-oleic oil and ordinary oil, the discriminant analysis model can be used to quickly identify batches of oil at one time, thereby improving the identification efficiency. At the same time, since the hyperspectral information of the oil can accurately characterize the oleic acid content therein, the discriminant analysis model constructed using the hyperspectral information can accurately identify the high-oleic oil, thereby improving the identification accuracy. Furthermore, since the one-time identification of batches of oil is achieved, and the model output discriminant value of batches of high-oleic oil usually presents a normal distribution, the normal distribution can be used to perform one-time authenticity identification of batches of high-oleic oil. In summary, the discriminant analysis model obtained by modeling the hyperspectral feature data of high-oleic oil and ordinary oil in this embodiment, combined with the normal distribution, can improve the efficiency and accuracy of oil identification, while achieving one-time authenticity identification of batches of high-oleic oil.

[0027] Figure 2 This is the second flow chart of the method for identifying high oleic acid oil mixed with ordinary oil provided in the embodiment of the present application; Figure 2 , the discriminant analysis model can be modeled based on the following method: 201. Performing black-and-white correction on hyperspectral images of a plurality of high-oleic oil grains and hyperspectral images of a plurality of ordinary oil grains to obtain a plurality of corrected oil grain images; 202. Extracting hyperspectral data from each corrected oil image; 203. Preprocess each hyperspectral data to obtain multiple target hyperspectral data; 204. Extract multiple hyperspectral feature data from each target hyperspectral data in descending order of importance; 205. The partial least squares discriminant analysis method is used to model multiple hyperspectral feature data and obtain a discriminant analysis model.

[0028] Take peanuts among oilseeds as an example: In step 201, hyperspectral images of 910 peanuts can be collected and black and white correction can be performed on the hyperspectral images of these 910 peanuts, including hyperspectral images of 455 high-oleic acid peanuts and hyperspectral images of 455 common peanuts, where the varieties of high-oleic acid peanuts include Yuhua 37, Jihua 51 and Jihua 915, and the varieties of common peanuts include Ehua 6, Yuhua 65 and Luhua 12.

[0029] Step 202 specifically includes: 202a. Filtering out a peanut body spectral image from each corrected peanut image according to a spectral difference between a peanut edge and a peanut background at a specific wavelength in each corrected peanut image; 202b, calculating the ratio of the sum of the spectral values ​​of each pixel in the peanut body spectral image to the number of pixels, and obtaining the central point spectral value of the peanut body spectral image; 202c. Determine the central point spectral value as the hyperspectral data in each corrected peanut image.

[0030] Through the above screening and calculation, the central point spectral value of the peanut main spectral image can be represented by the ratio of the sum of the spectral values ​​of each pixel in the peanut main spectral image to the number of pixels, and the central point spectral value can be further used to represent the hyperspectral data in each corrected peanut image, so that the extracted hyperspectral data can represent the characteristics of each corrected peanut image in a concise way.

[0031] In step 203, since the extracted hyperspectral data is still mixed with a lot of irrelevant information and noise, it is necessary to preprocess it to remove the irrelevant information and noise. Specifically, any one or more methods of background removal, boundary outlier elimination, standard normal transformation, derivation or multivariate scattering correction can be used. The derivation can adopt first-order derivation, and the derivation window size is 11, that is, the center points of all peanut body spectral images are drawn in the same spectral image, then the horizontal coordinate of the center point is the spectral wavelength, and the vertical coordinate is the spectral value of the center point, that is, the hyperspectral data. For the first center point, the average slope from the first center point to the eleventh center point is calculated as the first-order derivative; for the second center point, the average slope from the second center point to the twelfth center point is calculated as the first-order derivative, and so on. The first-order derivative of each center point will be affected by the 10 center points before and after it.

[0032] The number of smoothing points for derivation can be 2, that is, after calculating the first-order derivative, for the first center point, the average value of the first-order derivatives of 5 center points extending forward and backward from the first center point is calculated as the final first-order derivative of the first center point, and it is used as the target hyperspectral data of the first center point; for the second center point, the average value of the first-order derivatives of 5 points extending forward and backward from the second center point is calculated as the final first-order derivative of the second center point, and it is used as the target hyperspectral data of the first center point, and so on, to obtain the target hyperspectral data of each center point. It can be seen from the above that the first-order derivative of each center point will be affected by the two center points before and after it.

[0033] It should be noted that if there are less than 2 center points before or after any center point, it will be extended forward or backward to the actual center point, and the average value of the first-order derivative will be calculated.

[0034] In step 204, the 910 peanuts can be divided into three groups. The first group includes 151 high-oleic peanuts and 152 ordinary peanuts, the second group includes 152 high-oleic peanuts and 152 ordinary peanuts, and the third group includes 152 high-oleic peanuts and 151 ordinary peanuts.

[0035] In this embodiment, multiple hyperspectral feature data in the target hyperspectral data corresponding to the first group of peanuts can be extracted in descending order of importance to improve the stability and reliability of the data. The extraction method is not limited here. In this embodiment, a competitive adaptive reweighting method can be used for selective extraction.

[0036] In step 205, a partial least squares discriminant analysis method may be used to build a model for the hyperspectral feature data of the second group of peanuts to obtain a discriminant analysis model.

[0037] Furthermore, the hyperspectral data of the target peanut test set can be obtained according to the following steps: According to the hyperspectral images of the multiple peanuts to be tested, multiple target hyperspectral data of the multiple peanuts to be tested are obtained, and the multiple target hyperspectral data of the multiple peanuts to be tested are determined as the target peanut test set hyperspectral data. In this embodiment, the multiple target hyperspectral data corresponding to the third group of peanuts can be determined as the target peanut test set hyperspectral data.

[0038] This embodiment can eliminate irrelevant information and noise of the original hyperspectral images by performing black and white correction, preprocessing, feature extraction, and partial least squares discriminant analysis modeling on the hyperspectral images of multiple high-oleic peanuts and the hyperspectral images of multiple ordinary peanuts, and use important feature data to establish a discriminant analysis model with high recognition accuracy and efficiency.

[0039] In one embodiment, the hyperspectral feature data of the second group of peanuts is used as a training set, and the multiple target hyperspectral data of the third group of peanuts is used as a test set, and the discriminant analysis model is used to obtain the discriminant index of peanuts as shown in the following table: Table 1. Discrimination results of the discriminant analysis model

[0040] As shown in the above table, the partial least squares discriminant analysis method has the ability to analyze highly linear and noisy data, and its performance can be evaluated by sensitivity, specificity, accuracy and classification error, among which sensitivity indicates the proportion of high oleic peanuts correctly identified by the model, specificity indicates the proportion of common peanuts correctly identified by the model, accuracy indicates the proportion of high oleic and common peanuts correctly identified by the model as a whole, and classification error indicates the error rate of model identification.

[0041] The discrimination threshold of the model can be set to the average of the model output discrimination values ​​of similar numbers of high-oleic peanuts and ordinary peanuts. The discrimination threshold needs to be determined after obtaining the model output discrimination value when it is known that the peanuts are high-oleic peanuts or ordinary peanuts. After determining the discrimination threshold, the model output discrimination value of the unknown type of batch peanuts is compared with the discrimination threshold to identify whether each peanut in the batch is high-oleic peanuts or ordinary peanuts.

[0042] It can be seen from the above table that the accuracy of the discriminant analysis model is 99.01%, which proves that the model has good blind sample prediction ability.

[0043] In one embodiment, mixed identification can be performed on batches of high oleic peanuts of various varieties, and the mixed rate of the batch of high oleic peanuts can be calculated according to the number of identified common peanuts. The mixed rates of batches of high oleic peanuts of three different varieties are as follows: Table 2 Mixed rates of different varieties of high oleic acid peanuts in batches

[0044] It can be seen from the above table that since the types of all peanuts in a batch of peanuts can be known in one identification, the discriminant analysis model can realize a one-time detection of the mixed rate of batch high oleic acid peanuts.

[0045] Figure 3 This is a distribution diagram of discrimination values ​​when the mixing ratio is 5% in the method for identifying high oleic peanuts mixed with common peanuts provided in the embodiment of the present application; Figure 4 This is a distribution diagram of discrimination values ​​when the mixing ratio is 10% in the method for identifying high oleic acid peanuts mixed with common peanuts provided in the embodiment of the present application; Figure 5 This is a distribution diagram of discrimination values ​​when the mixing ratio is 15% in the method for identifying high oleic acid peanuts mixed with common peanuts provided in the embodiment of the present application; Figure 6 This is a distribution diagram of discrimination values ​​when the mixing ratio is 20% in the method for identifying high oleic acid peanuts mixed with common peanuts provided in the embodiment of the present application; Figure 7 This is a distribution diagram of discrimination values ​​when the mixing ratio is 25% in the method for identifying high oleic acid peanuts mixed with common peanuts provided in the embodiments of the present application.

[0046] In one embodiment, the authenticity of batches of high-oleic peanuts with five different mixed ratios can be identified. The five ratios can be 5%, 10%, 15%, 20% and 25%. The 99.5% confidence interval of the normal distribution is still used as the identification standard. The accuracy of the model output discrimination value relative to the true value of the batches of high-oleic peanuts with five mixed ratios is shown in the following table: Table 3 Accuracy of model output discriminant value relative to true value

[0047] It can be seen from the above table that batches of high oleic acid peanuts with these five mixed proportions can all be accurately identified.

[0048] Reference Figures 3 to 7 In the figure, the horizontal axis represents the discriminant value, and the vertical axis represents the probability density of the discriminant value. The model output discriminant values ​​of batch high oleic peanuts with these 5 mixed ratios all have parts that deviate from the normal distribution, so it can accurately identify that ordinary peanuts are mixed into the batch high oleic peanuts with these 5 mixed ratios.

[0049] The following is a description of the device for identifying ordinary oil mixed with high oleic oil provided in an embodiment of the present application. The device for identifying ordinary oil mixed with high oleic oil described below and the method for identifying ordinary oil mixed with high oleic oil described above can be referenced to each other.

[0050] Figure 8 Schematic diagram of the structure of the device for identifying high oleic acid oil mixed with ordinary oil provided in the embodiment of the present application. Figure 8 The present application provides a device for identifying high oleic acid oil mixed with ordinary oil, which may include: The near infrared spectrum data acquisition module 801 is used to: acquire the near infrared spectrum data of each oil in the target oil test set hyperspectral data; The discriminant analysis module 802 is used to: input the near infrared spectrum data into a discriminant analysis model to obtain a discriminant value of each oil output by the discriminant analysis model; The identification module 803 is used to: if the distribution of the discriminant values ​​of each oil conforms to the normal distribution, determine that the oil set corresponding to the hyperspectral data of the target oil test set is not mixed with ordinary oil; The discriminant analysis model is obtained by modeling the hyperspectral feature data of high oleic oil and ordinary oil using the discriminant analysis method. The high oleic oil is an oil whose oleic acid content meets the national standards, industry standards and other relevant standards, and the ordinary oil is an oil whose oleic acid content is lower than the national standards, industry standards and other relevant standards.

[0051] The present embodiment provides an identification device for high oleic acid oil mixed with ordinary oil, obtains near-infrared spectral data of each oil in the target oil test set hyperspectral data, inputs the near-infrared spectral data into a discriminant analysis model, and obtains a discriminant value of each oil output by the discriminant analysis model. If the distribution of the discriminant values ​​of each oil conforms to the normal distribution, it is determined that the oil set corresponding to the target oil test set hyperspectral data is not mixed with ordinary oil. The discriminant analysis model is obtained by modeling the hyperspectral feature data of high oleic acid oil and ordinary oil using the discriminant analysis method. High oleic acid oil is oil whose oleic acid content conforms to relevant standards such as national standards and industry standards, and ordinary oil is oil whose oleic acid content is lower than relevant standards such as national standards and industry standards. Since the discriminant analysis model is constructed using the hyperspectral feature data of high-oleic oil and ordinary oil, the discriminant analysis model can be used to quickly identify batches of oil at one time, thereby improving the identification efficiency. At the same time, since the hyperspectral information of the oil can accurately characterize the oleic acid content therein, the discriminant analysis model constructed using the hyperspectral information can accurately identify the high-oleic oil, thereby improving the identification accuracy. Furthermore, since the one-time identification of batches of oil is achieved, and the model output discriminant value of batches of high-oleic oil usually presents a normal distribution, the normal distribution can be used to perform one-time authenticity identification of batches of high-oleic oil. In summary, the discriminant analysis model obtained by modeling the hyperspectral feature data of high-oleic oil and ordinary oil in this embodiment, combined with the normal distribution, can improve the efficiency and accuracy of oil identification, while achieving one-time authenticity identification of batches of high-oleic oil.

[0052] In one embodiment, a modeling module (not shown in the figure) is further included for: Performing black-and-white correction on hyperspectral images of multiple grains of high-oleic oil and hyperspectral images of multiple grains of common oil to obtain multiple corrected oil images; Extracting hyperspectral data of each corrected oil image; Preprocessing each hyperspectral data to obtain multiple target hyperspectral data; Extract multiple hyperspectral feature data from each target hyperspectral data in descending order of importance; The plurality of hyperspectral feature data are modeled using a partial least squares discriminant analysis method to obtain the discriminant analysis model.

[0053] In one embodiment, the modeling module is specifically used to: According to the spectral difference between the oil edge and the oil background at a specific wavelength in each corrected oil image, the oil body spectral image is screened out from each corrected oil image; Calculating the ratio of the sum of the spectral values ​​of each pixel in the oil-body spectral image to the number of pixels to obtain the central point spectral value of the oil-body spectral image; The center point spectral value is determined as the hyperspectral data in each corrected oil image.

[0054] In one embodiment, the modeling module is specifically configured to: Each hyperspectral data is preprocessed by removing background, eliminating boundary abnormal points, standard normal transformation, derivative or multivariate scattering correction, so as to obtain multiple target hyperspectral data of multiple oil grains.

[0055] In one embodiment, a target oil test set hyperspectral data acquisition module (not shown in the figure) is further included, which is specifically used to: According to the hyperspectral images of the plurality of oils to be tested, a plurality of target hyperspectral data of the plurality of oil grains in the oils to be tested are obtained; A plurality of target hyperspectral data of a plurality of oil particles in the oil to be tested are determined as the target oil test set hyperspectral data.

[0056] In one embodiment, the confidence interval of the normal distribution is 99.5%.

[0057] Fig. 9 An example of a structural diagram of an electronic device is shown in FIG. Fig. 9 As shown, the electronic device may include: a processor 910, a communication interface 920, a memory 930 and a communication bus 940, wherein the processor 910, the communication interface 920 and the memory 930 communicate with each other via the communication bus 940. The processor 910 may call a computer program in the memory 930 to execute the steps of the method for identifying high oleic oil mixed with ordinary oil, for example including: Obtain near infrared spectrum data of each oil in the target oil test set hyperspectral data; Inputting the near infrared spectrum data into a discriminant analysis model to obtain a discriminant value of each oil output by the discriminant analysis model; If the distribution of the discriminant values ​​of each oil conforms to the normal distribution, it is determined that the oil set corresponding to the hyperspectral data of the target oil test set is not mixed with ordinary oil; The discriminant analysis model is obtained by modeling the hyperspectral feature data of high oleic oil and ordinary oil using the discriminant analysis method. The high oleic oil is an oil whose oleic acid content meets the national standards, industry standards and other relevant standards, and the ordinary oil is an oil whose oleic acid content is lower than the national standards, industry standards and other relevant standards.

[0058] In addition, the logic instructions in the above-mentioned memory 930 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0059] On the other hand, the embodiments of the present application further provide a computer program product, the computer program product comprising a computer program, the computer program can be stored on a non-transitory computer-readable storage medium, and when the computer program is executed by a processor, the computer can execute the steps of the method for identifying high oleic oil mixed with ordinary oil provided in the above embodiments, for example, including: Obtain near infrared spectrum data of each oil in the target oil test set hyperspectral data; Inputting the near infrared spectrum data into a discriminant analysis model to obtain a discriminant value of each oil output by the discriminant analysis model; If the distribution of the discriminant values ​​of each oil conforms to the normal distribution, it is determined that the oil set corresponding to the hyperspectral data of the target oil test set is not mixed with ordinary oil; The discriminant analysis model is obtained by modeling the hyperspectral feature data of high oleic oil and ordinary oil using the discriminant analysis method. The high oleic oil is an oil whose oleic acid content meets the national standards, industry standards and other relevant standards, and the ordinary oil is an oil whose oleic acid content is lower than the national standards, industry standards and other relevant standards.

[0060] On the other hand, an embodiment of the present application further provides a processor-readable storage medium, wherein the processor-readable storage medium stores a computer program, wherein the computer program is used to enable a processor to execute the steps of the method for identifying high oleic oil mixed with ordinary oil provided in the above embodiments, for example, including: Obtain near infrared spectrum data of each oil in the target oil test set hyperspectral data; Inputting the near infrared spectrum data into a discriminant analysis model to obtain a discriminant value of each oil output by the discriminant analysis model; If the distribution of the discriminant values ​​of each oil conforms to the normal distribution, it is determined that the oil set corresponding to the hyperspectral data of the target oil test set is not mixed with ordinary oil; The discriminant analysis model is obtained by modeling the hyperspectral feature data of high oleic oil and ordinary oil using the discriminant analysis method. The high oleic oil is an oil whose oleic acid content meets the national standards, industry standards and other relevant standards, and the ordinary oil is an oil whose oleic acid content is lower than the national standards, industry standards and other relevant standards.

[0061] The processor-readable storage medium can be any available medium or data storage device that can be accessed by the processor, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NANDFLASH), solid-state drive (SSD)), etc.

[0062] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0063] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0064] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for identifying high oleic acid oil mixed with common oil, characterized in that: include: Obtain near infrared spectrum data of each oil in the target oil test set hyperspectral data; Inputting the near infrared spectrum data into a discriminant analysis model to obtain a discriminant value of each oil output by the discriminant analysis model; If the distribution of the discriminant values ​​of each oil conforms to the normal distribution, it is determined that the oil set corresponding to the hyperspectral data of the target oil test set is not mixed with ordinary oil; The discriminant analysis model is obtained by modeling the hyperspectral feature data of high oleic oil and ordinary oil using the discriminant analysis method. The high oleic oil is an oil whose oleic acid content meets the national standards, industry standards and other relevant standards, and the ordinary oil is an oil whose oleic acid content is lower than the national standards, industry standards and other relevant standards.

2. The method for identifying high oleic oil mixed with common oil according to claim 1, characterized in that: The discriminant analysis model is obtained by modeling in the following way: Performing black-and-white correction on hyperspectral images of multiple grains of high-oleic oil and hyperspectral images of multiple grains of common oil to obtain multiple corrected oil images; Extracting hyperspectral data of each corrected oil image; Preprocessing each hyperspectral data to obtain multiple target hyperspectral data; Extract multiple hyperspectral feature data from each target hyperspectral data in descending order of importance; The plurality of hyperspectral feature data are modeled using a partial least squares discriminant analysis method to obtain the discriminant analysis model.

3. The method for identifying high oleic oil mixed with common oil according to claim 2, characterized in that: The step of extracting the hyperspectral data of each corrected oil image comprises: According to the spectral difference between the oil edge and the oil background at a specific wavelength in each corrected oil image, the oil body spectral image is screened out from each corrected oil image; Calculating the ratio of the sum of the spectral values ​​of each pixel in the oil-body spectral image to the number of pixels to obtain the central point spectral value of the oil-body spectral image; The center point spectral value is determined as the hyperspectral data in each corrected oil image.

4. The method for identifying high oleic oil mixed with common oil according to claim 2, characterized in that: The preprocessing of each hyperspectral data to obtain a plurality of target hyperspectral data includes: Each hyperspectral data is preprocessed by removing background, eliminating boundary abnormal points, standard normal transformation, derivative or multivariate scattering correction, so as to obtain multiple target hyperspectral data of multiple oil grains.

5. The method for identifying high oleic oil mixed with common oil according to claim 2, characterized in that: The target oil test set hyperspectral data is obtained based on the following method: According to the hyperspectral images of the plurality of oils to be tested, a plurality of target hyperspectral data of the plurality of oil grains in the oils to be tested are obtained; A plurality of target hyperspectral data of a plurality of oil particles in the oil to be tested are determined as the target oil test set hyperspectral data.

6. The method for identifying high oleic oil mixed with common oil according to claim 1, characterized in that: The confidence interval for the normal distribution is 99.5%.

7. A device for identifying high oleic acid oil mixed with ordinary oil, characterized in that: include: The near infrared spectrum data acquisition module is used to: acquire the near infrared spectrum data of each oil in the target oil test set hyperspectral data; A discriminant analysis module, used to: input the near infrared spectrum data into a discriminant analysis model to obtain a discriminant value of each oil output by the discriminant analysis model; The identification module is used to: if the distribution of the discriminant values ​​of each oil conforms to the normal distribution, determine that the oil set corresponding to the hyperspectral data of the target oil test set is not mixed with ordinary oil; The discriminant analysis model is obtained by modeling the hyperspectral feature data of high oleic oil and ordinary oil using the discriminant analysis method. The high oleic oil is an oil whose oleic acid content meets the national standards, industry standards and other relevant standards, and the ordinary oil is an oil whose oleic acid content is lower than the national standards, industry standards and other relevant standards.

8. An electronic device comprising a processor and a memory storing a computer program, characterized in that: When the processor executes the computer program, the steps of the method for identifying high oleic oil mixed with ordinary oil as described in any one of claims 1 to 6 are implemented.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method for identifying high oleic oil mixed with ordinary oil as described in any one of claims 1 to 6 are implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for identifying high oleic oil mixed with ordinary oil as described in any one of claims 1 to 6 are implemented.

Images